MAS Architectural Model for Dialog Systems with Advancing Conversations

Large language models (LLMs) like ChatGPT have demonstrated the ability to perform a variety of natural language processing (NLP) tasks. However, it's unclear whether ChatGPT can serve as a task-oriented dialogue system. In this paper, we evaluate the impact of ChatGPT on task-oriented dialogue (TOD) systems and perform a comprehensive analysis to learn its benefits and challenges. We find that ChatGPT performs well on relatively simple dialogue understanding tasks such as intent detection and slot filling, but fails to understand complex multi-turn conversations and interact with Knowledge Base(KB) in dialogue state tracking and response generation. Future LLM-based TOD work should pay more attention to (1) incorporating domain knowledge (2) understanding complex instructions (3) modeling long-term memory (4) interacting with external knowledge bases.

Task-Oriented Dialogue (TOD) systems are designed to carry out specific tasks by tracking dialogue states and generating appropriate responses to help users achieve defined goals. Recently, end-to-end dialogue models pre-trained based on large datasets have shown promising performance in the conversational system. However, they share the same parameters to train tasks of the dialogue system (NLU, DST, NLG), so debugging each task is challenging. Also, they require a lot of effort to fine-tune large parameters to create a task-oriented chatbot, making it difficult for non-experts to handle. Therefore, we intend to train relatively lightweight and fast models compared to PLM. In this paper, we propose an End-to-end TOD system with Task-Optimized Adapters which learn independently per task, adding only small number of parameters after fixed layers of pre-trained network. We also enhance the performance of the DST and NLG modules through reinforcement learning, overcoming the learning curve that has lacked at the adapter learning and enabling the natural and consistent response generation that is appropriate for the goal. Our method is a model-agnostic approach and does not require prompt-tuning as only input data without a prompt. As results of the experiment, our method shows competitive performance on the MultiWOZ benchmark compared to the existing end-to-end models. In particular, we attain state-of-the-art performance on the DST task of 2.2 dataset.

Pre-trained encoder-decoder models are widely applied in Task-Oriented Dialog (TOD) systems on the session level, mainly focusing on modeling the dialog semantic information. Dialogs imply structural information indicating the interaction among user utterances, belief states, database search results, system acts and responses, which is also crucial for TOD systems. In addition, for the system acts, additional pre-training and datasets are considered to improve their accuracies, undoubtedly introducing a burden. Therefore, a novel end-to-end TOD system named Winnie is proposed in this paper to improve the TOD performance. First, to make full use of the intrinsic structural information, supervised contrastive learning is adopted to narrow the gap in the representation space between text representations of the same category and enlarge the overall continuous representation margin between text representations of different categories in dialog context. Then, a system act classification task is introduced for policy optimization during fine-tuning. Empirical results show that Winnie substantially improves the performance of the TOD system. By introducing the supervised contrastive and system act classification losses, Winnie achieves state-of-the-art results on benchmark datasets, including MultiWOZ2.2, In-Car, and Camrest676. Their end-to-end combined scores are improved by 3.2, 1.9, and 1.1 points, respectively.

Task-oriented dialogue systems have become crucial for users to interact with machines and computers using natural language. One of its key components is the dialogue manager, which guides the conversation towards a good goal for the user by providing the best possible response. Previous works have proposed rule-based systems, reinforcement learning, and supervised learning as solutions for correct dialogue management; in other words, select the best response given input by the user. This work explores the impact of dataset quality on the performance of dialogue managers. We delve into potential errors in popular datasets, such as Multiwoz 2.1 and SGD. For our investigation, we developed a synthetic dialogue generator to regulate the type and magnitude of errors introduced. Our findings suggest that dataset inaccuracies, like mislabeling, might play a significant role in the challenges faced in dialogue management.

Dialog management plays an important role in the task-oriented dialog system. Most of the previous works divide dialog management into state tracker and action selector. The two parts are modeled separately and implemented in a pipelined way, which suffers from the problem of error accumulation, and the feedback signal from action selector cannot be propagated to state tracker and natural language understanding module. This paper proposes a word-based partially observable Markov decision processes' dialog management that integrates natural language understanding, state tracker, and action selector into an end-to-end architecture. Our proposed dialog management takes the words from user utterances as inputs and then produces optimal action as well as slot values of natural language understanding which are necessary for response generation. To this end, we propose a hybrid learning method, which integrates reinforcement learning and supervised learning, to optimize the action selector and slot filler jointly. In addition, we develop a high-return prioritized experience replay to speed up the convergence of the training process. The experimental results show that the proposed dialog management outperforms four strong baselines in a series of different dialog tasks. A human user's evaluation also shows the same results. The high-return prioritized experience replay accelerates the convergence effectively, especially in the scenario in which the proposed dialog management works on more complex tasks.

A framework for building closed-domain chat dialogue systems

Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on both structured and unstructured knowledge. To address this task, we propose a TOD system with hybrid knowledge management, HyKnow. It extends the belief state to manage both structured and unstructured knowledge, and is the first end-to-end model that jointly optimizes dialog modeling grounded on these two kinds of knowledge. We conduct experiments on the modified version of MultiWOZ 2.1 dataset, where dialogs are grounded on hybrid knowledge. Experimental results show that HyKnow has strong end-to-end performance compared to existing TOD systems. It also outperforms the pipeline knowledge management schemes, with higher unstructured knowledge retrieval accuracy.

This paper presents a new framework for implementing a dialogue manager, making it possible to infer new information in the course of the interaction as well as generating responses from the virtual agent. The approach relies on a specific organization of knowledge bases, including the creation of a common ground and a belief base. Moreover, the same type of rules implement both inference and control of the dialogue. This approach is implemented within a dialogue system for training doctors to break bad news (ACORFORMed).

Natural language understanding is a critical module in task-oriented dialogue systems. Recently, state-of-the-art approaches use deep learning methods and transformers to improve the performance of dialogue systems. In this work, we propose a natural language understanding model with a specific-shopping named entity recognizer using a joint learning-based BERT transformer for task-oriented dialogue systems in the Persian Language. Since there is no published available dataset for Persian online shopping dialogue systems, to tackle the lack of data, we propose two methods for generating training data: fully-simulated and semi-simulated method. We created a simulated dataset with a hybrid of rule-based and template-based generation methods and a semi-simulated dataset where the language generation part is done by a human to increase the quality of the dataset. Our experiments with the natural language understanding module show that a combination of the datasets can improve results. These dataset generation methods can apply in other domains for low-resource languages in task-oriented dialogue systems too to solve the cold start problem of datasets.

Building task-oriented dialogue systems has become a topic of interest in the research community and industry. The task-oriented dialogue system is a closed-domain dialogue system that can perform specific tasks for users. The natural language understanding module of a task-oriented dialogue system is crucial because it is related to a task-oriented dialogue system that provides correctional services for users. The natural language understanding module of a task-oriented dialogue system performs two tasks: intent detection and slot filling. The intent detection task can be regarded as a text classification task; a classification model is trained to predict the intention of the user from the user’s input information. The slot filling task can be regarded as a sequence analysis task; a sequence analysis model is trained to predict the details of the user’s intention. In this paper, we proposed a novel model based on a transformer encoder for intent detection and slot filling. It follows the encoder-decoder structure, including a vanilla Transformer encoder, a bidirectional LSTM encoder, a linear classification decoder for intent detection, and a conditional random field decoder for slot filling. The experimental results on two public datasets show that our proposed model outperforms the existing methods based on the Transformer and can be combined with BERT to achieve better intent detection and slot filling results.

Last few decades have witnessed substantial breakthroughs on several areas of speech and language understanding research, specifically for building human to machine conversational dialog systems. Dialog systems, also known as interactive conversational agents, virtual agents or sometimes chatbots, are useful in a wide range of applications ranging from technical support services to language learning tools and entertainment. Recent success in deep neural networks has spurred the research in building data-driven dialog models. In this chapter, we present state-of-the-art neural network architectures and details on each of the components of building a successful dialog system using deep learning. Task-oriented dialog systems would be the focus of this chapter, and later different networks are provided for building open-ended non-task-oriented dialog systems. Furthermore, to facilitate research in this area, we have a survey of publicly available datasets and software tools suitable for data-driven learning of dialog systems. Finally, appropriate choice of evaluation metrics are discussed for the learning objective.

End-to-end task-oriented dialogue systems rely heavily on an understanding of the dialog history. This often faces the challenge of inferring which dialog history information is critical to generating responses. In this paper, we address this challenge by leveraging a dialog history manager component that dynamically focuses on dialog history memory. It performs multiple add and forget operations by fusing an enhanced entity representation of dialog history and Knowledge Base (KB) information as queries, remembering entities relevant to responses and filtering out unimportant information. Experimental results on an open task-oriented dialogue dataset show that our model outperforms the baseline system in terms of effectiveness and produces contextually consistent responses.

Dialogue systems are a popular natural language processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on this task are carried out, and most of them are deep learning based due to their outstanding performance. In this survey, we mainly focus on the deep learning based dialogue systems. We comprehensively review state-of-the-art research outcomes in dialogue systems and analyze them from two angles: model type and system type. Specifically, from the angle of model type, we discuss the principles, characteristics, and applications of different models that are widely used in dialogue systems. This will help researchers acquaint these models and see how they are applied in state-of-the-art frameworks, which is rather helpful when designing a new dialogue system. From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related. Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research. Finally, some possible research trends are identified based on the recent research outcomes. To the best of our knowledge, this survey is the most comprehensive and up-to-date one at present for deep learning based dialogue systems, extensively covering the popular techniques. We speculate that this work is a good starting point for academics who are new to the dialogue systems or those who want to quickly grasp up-to-date techniques in this area.

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility. However, it is hard for developers to maintain the dialogue logic when the scenarios get more and more complex. On the other hand, data-driven dialogue systems, usually with end-to-end structures, are popular in academic research and easier to deal with complex conversations, but such methods require plenty of training data and the behaviors are less interpretable. In this paper, we propose a method to leverages the strength of both rule-based and data-driven dialogue managers (DM). We firstly introduce the DM of Carina Dialog System (CDS, an advanced industrial dialogue system built by Microsoft). Then we propose the "model-trigger" design to make the DM trainable thus scalable to scenario changes. Furthermore, we integrate pre-trained models and empower the DM with few-shot capability. The experimental results demonstrate the effectiveness and strong few-shot capability of our method.

We proposed a dialog system using a weighted finite-state transducer (WFST) in which user concept and system action tags are input and output of the transducer, respectively. The WFST-based platform for dialog management enables us to combine various statistical models for dialog management (DM), user input understanding and system action generation, and then search the best system action in response to user inputs among multiple hypotheses. To test the potential of the WFST-based DM platform using statistical models, we constructed a dialog system using a human-to-human spoken dialog corpus for hotel reservation, which is annotated with Interchange Format (IF). A scenario WFST and a spoken language understanding (SLU) WFST were obtained from the corpus and then composed together and optimized. We evaluated the detection accuracy of the system next action tags using Mean Reciprocal Ranking (MRR). Finally, we constructed a full WFST-based dialog system by composing SLU, scenario and sentence generation (SG) WFSTs. Humans read the system responses in natural language and judged the quality of the responses. We confirmed that the WFST-based DM platform was capable of handling various spoken language and scenarios when the user concept and system action tags are consistent and distinguishable.